Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional statements or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.66
    PK
    -0.62
    oph
    -0.61
    ophon
    -0.60
    ãĥ¥
    -0.60
    ãĤ´ãĥ³
    -0.60
    NZ
    -0.58
    SB
    -0.57
    eteenth
    -0.55
    FIELD
    -0.55
    POSITIVE LOGITS
     however
    0.87
     please
    0.78
     namely
    0.74
     aka
    0.73
    tein
    0.72
     THEN
    0.72
    tan
    0.72
     chances
    0.71
    Downloadha
    0.71
    then
    0.70
    Act Density 0.354%

    No Known Activations